Multi-spatial-attention U-Net: a novel framework for automated gallbladder segmentation on CT images.
Authors
Affiliations (10)
Affiliations (10)
- Department of Radiation Oncology, The Affiliated Hospital of Qingdao University, Qingdao, China.
- Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China.
- The Affiliated Hospital of Qingdao University, Qingdao University, Qingdao, China. [email protected].
- School of Pharmacy, Qingdao University, Qingdao, China. [email protected].
- Qingdao Cancer Institute, Qingdao University, Qingdao, China. [email protected].
- Department of Radiology, People's Hospital of Rizhao, Rizhao, China.
- Qingdao Cancer Institute, Qingdao University, Qingdao, China.
- Department of Radiation Oncology, Qingdao Chengyang District People's Hospital, Qingdao, China.
- Department of Oncology, Qingdao Sixth People's Hospital, Qingdao, China.
- Department of Radiation Oncology, The Affiliated Hospital of Qingdao University, Qingdao, China. [email protected].
Abstract
This study aimed to construct a novel model, Multi-Spatial Attention U-Net (MSAU-Net) by incorporating our proposed Multi-Spatial Attention (MSA) block into the U-Net for the automated segmentation of the gallbladder on CT images. The gallbladder dataset consists of CT images of retrospectively-collected 152 liver cancer patients and corresponding ground truth delineated by experienced physicians. Our proposed MSAU-Net model was transformed into two versions V1(with one Multi-Scale Feature Extraction and Fusion (MSFEF) module in each MSA block) and V2 (with two parallel MSEFE modules in each MSA blcok). The performances of V1 and V2 were evaluated and compared with four other derivatives of U-Net or state-of-the-art models quantitatively using seven commonly-used metrics, and qualitatively by comparison against experienced physicians' assessment. MSAU-Net V1 and V2 models both outperformed the comparative models across most quantitative metrics with better segmentation accuracy and boundary delineation. The optimal number of MSA was three for V1 and two for V2. Qualitative evaluations confirmed that they produced results closer to physicians' annotations. External validation revealed that MSAU-Net V2 exhibited better generalization capability. The MSAU-Net V1 and V2 both exhibited outstanding performance in gallbladder segmentation, demonstrating strong potential for clinical application. The MSA block enhances spatial information capture, improving the model's ability to segment small and complex structures with greater precision. These advantages position the MSAU-Net V1 and V2 as valuable tools for broader clinical adoption.